Architect –Generative AI

SWI - Innovation Delivered; New Delhi; On-site; INR 9,074,410 - 11,796,733; Full time

Job summary

A technology solutions provider is seeking an experienced Generative AI Architect with robust backend engineering skills. The successful candidate will architect and develop scalable, production-grade Generative AI systems utilizing Python and microservices. Key responsibilities include designing and implementing RAG and LLM orchestration workflows while ensuring security and performance. Candidates should ideally have over 10 years of Python experience, strong skills in FastAPI and Flask, and familiarity with Generative AI frameworks and microservices architecture.

Qualifications

• 10+ years of Python programming experience with a focus on backend engineering.
• At least 3 years of hands-on experience with Generative AI systems.
• Strong understanding of microservices and cloud-native architecture.

Responsibilities

• Architect and build Python-based GenAI microservices and REST APIs.
• Design and implement retrieval-augmented generation and orchestration workflows.
• Ensure scalability and performance of AI services.

Skills

Python

FastAPI

Flask

Async programming

Distributed systems

Generative AI

Microservices architecture

Cloud-native architecture

LangChain

LlamaIndex

Hugging Face

Vector databases

Job description

Seeking an experienced Generative AI Architect with strong backend engineering expertise to design and deliver scalable, production-grade GenAI systems using Python and microservices.

Key Responsibilities

• Architect and build Python-based GenAI microservices and REST APIs (FastAPI/Flask)
• Design and implement RAG, LLM orchestration, and agentic workflows
• Ensure scalability, security, reliability, and performance of AI services
• Collaborate with DevOps, ML, and Data Science teams, mentor engineers

Required Skills

• 10+ years Python; strong in FastAPI, Flask, async, and distributed systems
• 3+ years hands-on Generative AI experience (RAG, LLM frameworks)
• Microservices and cloud-native architecture (Azure preferred)
• Experience with LangChain, LlamaIndex, Hugging Face
• Vector databases (FAISS, Pinecone, Weaviate)

Nice to Have

• LLM fine-tuning, prompt engineering, MLOps, AI observability